Mass-target image matching algorithm based on self-constructed multi-window
-
摘要: 針對大批量芯片生產中視覺檢測難題,提出了一種基于多窗體結構的多目標匹配算法,實現了多窗體結構的自構建.結合螺旋形特征鏈對最多近似點距離(MCD)進行了改進,提高了算法速度和魯棒性.通過實驗證實:該算法較好地完成了大批量芯片識別任務;該算法除了具有高速度和高精確度的優點之外,還具有其他算法不具備的柔性.
-
關鍵詞:
- 視覺檢測 /
- 芯片生產 /
- 多窗體 /
- 最多近似點距離(MCD)
Abstract: An algorithm of mass-target image matching for vision measurement in mass chip production was put forward to carry out multi-window self-construction. Spiral character chain was used to modify maximum close distance (MCD) for improving the speed and robustness. Experimental results confirm that the assignment of recognizing mass chips is achieved by the algorithm. Beside the advantages of high speed and precision, it is flexible compared with other algorithms.-
Key words:
- vision measurement /
- chip production /
- multi-window /
- maximum close distance(MCD)
-
點擊查看大圖
計量
- 文章訪問數: 158
- HTML全文瀏覽量: 40
- PDF下載量: 3
- 被引次數: 0
下載:
